Search
@mukundakatta/prompt-injection-shield-mcp
mukundakatta
MCP server exposing prompt-injection-shield: scan untrusted text for prompt-injection signals, score risk, strip dangerous lines. Built for Claude Desktop, Cursor, Cline, Windsurf, and Zed.
...moreowthorize
iyush004
Block unsafe AI-agent tool calls before they execute. SQL DDL, SSRF, shell metacharacters, path traversal, and custom rules.
...moreAgentDoG-Llama3.1-8B-i1-GGUF
mradermacher
AI model: mradermacher/AgentDoG-Llama3.1-8B-i1-GGUF
powchallenge_server
simon-bertrand
Server validation library for the POW Captcha ecosystem.
rafapra3008/cervellaswarm
[](https://glama.ai/mcp/servers/rafapra3008/cervellaswarm) 🐍 🏠 🍎 🪟 🐧 - Verify AI agent communication protocols using session types. Formal specification with Lean 4 proofs, linter, formatter, and LSP. Catches deadlocks and role violations before deployment.
...morecaptcha-svg-generator
prathamesh.c
A lightweight, customizable Node.js library to generate SVG CAPTCHA images with random characters, noise lines, and custom fonts using opentype.js. Ideal for Express.js, authentication, and bot protection.
...moreClosemask
huilangsh
Privacy shield for AI Agents: Automatically mask PII and credentials before sending to LLM APIs. Supports tool calls & streaming.AI Agent 隐私防护盾：在调用 LLM API 前自动遮罩个人身份信息和凭据。支持工具调用与流式响应。
...moreexpress-jwt-permissions
michieldemey
Express middleware for JWT permissions
ra-in-memory-jwt
alexisjanvier
Manage React-admin authentication with jwt in memory, not in local storage
strapi-plugin-admin-2fa-by-email
anvpro
Two-factor email authentication for Strapi 5 admin panel
kernel-js-lite
wuyuchentr
Embedded JavaScript kernel — pure Node.js JS runtime for safe execution of untrusted code. Tokenizer, parser, interpreter with scopes, closures, built-in objects, host API bindings, and resource limits. (中文 / English / 日本語 / 한국어)
...more1ai-skills
algoexperthub
1282 production-ready AI agent skills with self-evolving meta-skills — cybersecurity, SEO, trading, marketing, automation, devops, content, financial services
...more@h3l1os/mp4vault
h3l1os-sol
Hide and extract files within MP4, JPEG, and PNG containers with AES-256-GCM encryption
llm-witch-hunt
incrediblecrab
LLM Witch-Hunt: Detect and audit AI/LLM-generated code and API usage in your codebase
mezzo-guard
Mezzo Guard is a Python SDK designed to add a protective layer to LLM applications attacks such as jailbreaking and prompt injection, powered by custom-trained models adapted to recent trends. Mezzo Guard can be easily added into your pipeline, offering great protection with little effort.
...more@froggychips/mcp-vault
froggychips
Deterministic registry + integrity scanner for Model Context Protocol servers. Make MCP supply-chain boring.
@twira/cli
cmidd
Coding power tools for AI agents. Deliver better code, faster and safer.
Windows Computer Use Mcp
sandraschi
Windows computer use MCP server -- click, screenshot, OCR, GUI automation for AI agents
genversion
xeli
A command line utility to read version from package.json and attach it into your module as a property
@node-rs/jsonwebtoken
broooooklyn
Rust jsonwebtoken binding for Node.js